{"id":"W2848493808","doi":"10.48550/arxiv.1808.06167","title":"Source-Critical Reinforcement Learning for Transferring Spoken Language Understanding to a New Language","year":2018,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Reinforcement learning; Sentence; Natural language processing; Artificial intelligence; Domain (mathematical analysis); Adaptation (eye); Spoken language; Task (project management); Language model","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0002025574,0.0001306273,0.0001340202,0.0001596261,0.0002374248,0.00008875698,0.0005288691,0.000057031,0.00004753716],"category_scores_gemma":[0.0001045701,0.0001517067,0.00008170572,0.0003518067,0.00004017362,0.0003385003,0.0001771182,0.0001235934,0.00005633467],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001879046,"about_ca_system_score_gemma":0.00005919642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002232941,"about_ca_topic_score_gemma":0.0000870101,"domain_scores_codex":[0.9988749,0.00003203678,0.0001217614,0.0004898285,0.0000800663,0.0004014132],"domain_scores_gemma":[0.9992279,0.0001503967,0.0000245231,0.0003265839,0.00003716434,0.0002333729],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001275431,0.00003327192,0.0008844882,0.00006322376,0.00005924337,0.0001154621,0.03880899,0.2300808,0.002952019,0.717788,0.0002091513,0.008877841],"study_design_scores_gemma":[0.0007859537,0.0002496782,0.00002510638,0.00007937037,0.00002660576,0.000005257229,0.004747942,0.9889571,0.001503641,0.002493954,0.0008317093,0.0002936556],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1973614,0.0000107608,0.8005533,0.0001750732,0.0001219166,0.0001587784,3.130784e-7,0.0001829758,0.001435509],"genre_scores_gemma":[0.9875126,0.000001444291,0.007801641,0.0002281679,0.0001882384,5.278104e-7,0.000001177875,0.00001317346,0.004253036],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7927517,"threshold_uncertainty_score":0.6186422,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1008120889274694,"score_gpt":0.2255297749164429,"score_spread":0.1247176859889735,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}